wayfarer 0.0.3 → 0.4.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.github/workflows/ci.yaml +32 -0
- data/.gitignore +3 -4
- data/.rubocop.yml +25 -9
- data/.ruby-version +1 -1
- data/Dockerfile +5 -0
- data/Gemfile +1 -7
- data/Gemfile.lock +212 -0
- data/RELEASING.md +17 -0
- data/Rakefile +38 -90
- data/bin/wayfarer +1 -111
- data/docker-compose.yml +32 -0
- data/docs/cookbook/querying_html.md +42 -0
- data/docs/cookbook/screenshots.md +27 -0
- data/docs/cookbook/user_agent.md +7 -0
- data/docs/guides/browser_automation/capybara.md +3 -0
- data/docs/guides/browser_automation/ferrum.md +37 -0
- data/docs/guides/browser_automation/selenium.md +59 -0
- data/docs/guides/callbacks.md +27 -34
- data/docs/guides/configuration.md +20 -171
- data/docs/guides/error_handling.md +18 -33
- data/docs/guides/jobs.md +75 -0
- data/docs/guides/networking.md +20 -0
- data/docs/guides/pages.md +52 -0
- data/docs/guides/performance.md +22 -0
- data/docs/guides/tasks.md +38 -0
- data/docs/index.md +34 -68
- data/docs/reference/api/base.md +162 -0
- data/docs/reference/api/route.md +182 -0
- data/docs/reference/cli.md +139 -0
- data/docs/reference/environment_variables.md +85 -0
- data/lib/wayfarer/base.rb +60 -0
- data/lib/wayfarer/cli/base.rb +23 -0
- data/lib/wayfarer/cli/generate.rb +17 -0
- data/lib/wayfarer/cli/job.rb +58 -0
- data/lib/wayfarer/cli/route.rb +27 -0
- data/lib/wayfarer/cli/route_printer.rb +116 -0
- data/lib/wayfarer/cli/runner.rb +34 -0
- data/lib/wayfarer/cli/templates/Gemfile.tt +5 -0
- data/lib/wayfarer/cli/templates/job.rb.tt +8 -0
- data/lib/wayfarer/config.rb +67 -0
- data/lib/wayfarer/gc.rb +19 -0
- data/lib/wayfarer/middleware/chain.rb +19 -0
- data/lib/wayfarer/middleware/dedup.rb +25 -0
- data/lib/wayfarer/middleware/fetch.rb +32 -0
- data/lib/wayfarer/middleware/normalize.rb +25 -0
- data/lib/wayfarer/middleware/router.rb +21 -0
- data/lib/wayfarer/middleware/stage.rb +23 -0
- data/lib/wayfarer/middleware/worker.rb +47 -0
- data/lib/wayfarer/networking/ferrum.rb +70 -0
- data/lib/wayfarer/networking/healer.rb +21 -0
- data/lib/wayfarer/networking/net_http.rb +52 -0
- data/lib/wayfarer/networking/pool.rb +34 -0
- data/lib/wayfarer/networking/result.rb +18 -0
- data/lib/wayfarer/networking/selenium.rb +70 -0
- data/lib/wayfarer/page.rb +15 -71
- data/lib/wayfarer/parsing/json.rb +17 -0
- data/lib/wayfarer/parsing/xml.rb +17 -0
- data/lib/wayfarer/redis/barrier.rb +36 -0
- data/lib/wayfarer/redis/connection.rb +13 -0
- data/lib/wayfarer/redis/counter.rb +29 -0
- data/lib/wayfarer/redis/pool.rb +18 -0
- data/lib/wayfarer/redis/version.rb +19 -0
- data/lib/wayfarer/routing/custom_matcher.rb +21 -0
- data/lib/wayfarer/routing/dsl.rb +57 -0
- data/lib/wayfarer/routing/host_matcher.rb +23 -0
- data/lib/wayfarer/routing/path_finder.rb +46 -0
- data/lib/wayfarer/routing/path_matcher.rb +46 -0
- data/lib/wayfarer/routing/{query_rule.rb → query_matcher.rb} +24 -16
- data/lib/wayfarer/routing/result.rb +15 -0
- data/lib/wayfarer/routing/root_route.rb +7 -0
- data/lib/wayfarer/routing/route.rb +41 -0
- data/lib/wayfarer/routing/scheme_matcher.rb +21 -0
- data/lib/wayfarer/routing/suffix_matcher.rb +21 -0
- data/lib/wayfarer/routing/target_route.rb +7 -0
- data/lib/wayfarer/routing/url_matcher.rb +21 -0
- data/lib/wayfarer/serializer.rb +17 -0
- data/lib/wayfarer/stringify.rb +41 -0
- data/lib/wayfarer/task.rb +34 -0
- data/lib/wayfarer.rb +47 -58
- data/mkdocs.yml +47 -0
- data/requirements.txt +1 -0
- data/spec/base_spec.rb +219 -0
- data/spec/cli/generate_spec.rb +39 -0
- data/spec/cli/job_spec.rb +74 -0
- data/spec/cli/version_spec.rb +13 -0
- data/spec/config_spec.rb +144 -0
- data/spec/factories/queue/chain.rb +11 -0
- data/spec/factories/queue/middleware.rb +15 -0
- data/spec/factories/queue/page.rb +78 -0
- data/spec/factories/queue/task.rb +12 -0
- data/spec/fixtures/dummy_job.rb +7 -0
- data/spec/gc_spec.rb +61 -0
- data/spec/middleware/chain_spec.rb +96 -0
- data/spec/middleware/dedup_spec.rb +76 -0
- data/spec/middleware/fetch_spec.rb +72 -0
- data/spec/middleware/normalize_spec.rb +28 -0
- data/spec/middleware/router_spec.rb +46 -0
- data/spec/middleware/stage_spec.rb +39 -0
- data/spec/middleware/worker_spec.rb +90 -0
- data/spec/networking/adapter.rb +135 -0
- data/spec/networking/ferrum_spec.rb +28 -0
- data/spec/networking/healer_spec.rb +46 -0
- data/spec/networking/net_http_spec.rb +37 -0
- data/spec/networking/pool_spec.rb +42 -0
- data/spec/networking/selenium_spec.rb +28 -0
- data/spec/page_spec.rb +21 -12
- data/spec/{parsers/json_parser_spec.rb → parsing/json_spec.rb} +5 -4
- data/spec/{parsers/xml_parser_spec.rb → parsing/xml_spec.rb} +3 -2
- data/spec/redis/barrier_spec.rb +78 -0
- data/spec/redis/counter_spec.rb +32 -0
- data/spec/redis/pool_spec.rb +18 -0
- data/spec/redis/version_spec.rb +13 -0
- data/spec/routing/custom_matcher_spec.rb +31 -0
- data/spec/routing/dsl_spec.rb +98 -0
- data/spec/routing/host_matcher_spec.rb +49 -0
- data/spec/routing/integration_spec.rb +110 -0
- data/spec/routing/path_finder_spec.rb +33 -0
- data/spec/routing/path_matcher_spec.rb +43 -0
- data/spec/routing/{query_rule_spec.rb → query_matcher_spec.rb} +39 -26
- data/spec/routing/root_route_spec.rb +29 -0
- data/spec/routing/route_spec.rb +43 -0
- data/spec/routing/scheme_matcher_spec.rb +25 -0
- data/spec/routing/{filetypes_rule_spec.rb → suffix_matcher_spec.rb} +14 -13
- data/spec/routing/uri_matcher_spec.rb +27 -0
- data/spec/spec_helpers.rb +65 -38
- data/spec/stringify_spec.rb +23 -0
- data/{support → spec/support}/static/finders.html +0 -0
- data/{support → spec/support}/static/graph/details/a.html +0 -0
- data/{support → spec/support}/static/graph/details/b.html +0 -0
- data/{support → spec/support}/static/graph/index.html +0 -0
- data/{support → spec/support}/static/json/dummy.json +0 -0
- data/{support → spec/support}/static/links/links.html +0 -0
- data/{support → spec/support}/static/xml/dummy.xml +0 -0
- data/{support → spec/support}/test_app.rb +9 -2
- data/spec/task_spec.rb +27 -0
- data/spec/wayfarer_spec.rb +2 -13
- data/wayfarer.gemspec +39 -42
- metadata +191 -368
- data/.travis.yml +0 -5
- data/Changelog.md +0 -10
- data/README.md +0 -21
- data/benchmark/frontiers.rb +0 -143
- data/docs/.gitignore +0 -2
- data/docs/_config.yml +0 -15
- data/docs/_includes/base.html +0 -7
- data/docs/_includes/head.html +0 -10
- data/docs/_includes/navigation.html +0 -187
- data/docs/_layouts/default.html +0 -42
- data/docs/_sass/base.scss +0 -439
- data/docs/_sass/variables.scss +0 -24
- data/docs/_sass/vendor/bourbon/_bourbon-deprecate.scss +0 -19
- data/docs/_sass/vendor/bourbon/_bourbon-deprecated-upcoming.scss +0 -425
- data/docs/_sass/vendor/bourbon/_bourbon.scss +0 -90
- data/docs/_sass/vendor/bourbon/addons/_border-color.scss +0 -29
- data/docs/_sass/vendor/bourbon/addons/_border-radius.scss +0 -48
- data/docs/_sass/vendor/bourbon/addons/_border-style.scss +0 -28
- data/docs/_sass/vendor/bourbon/addons/_border-width.scss +0 -28
- data/docs/_sass/vendor/bourbon/addons/_buttons.scss +0 -69
- data/docs/_sass/vendor/bourbon/addons/_clearfix.scss +0 -25
- data/docs/_sass/vendor/bourbon/addons/_ellipsis.scss +0 -30
- data/docs/_sass/vendor/bourbon/addons/_font-stacks.scss +0 -31
- data/docs/_sass/vendor/bourbon/addons/_hide-text.scss +0 -27
- data/docs/_sass/vendor/bourbon/addons/_margin.scss +0 -29
- data/docs/_sass/vendor/bourbon/addons/_padding.scss +0 -29
- data/docs/_sass/vendor/bourbon/addons/_position.scss +0 -51
- data/docs/_sass/vendor/bourbon/addons/_prefixer.scss +0 -66
- data/docs/_sass/vendor/bourbon/addons/_retina-image.scss +0 -27
- data/docs/_sass/vendor/bourbon/addons/_size.scss +0 -56
- data/docs/_sass/vendor/bourbon/addons/_text-inputs.scss +0 -118
- data/docs/_sass/vendor/bourbon/addons/_timing-functions.scss +0 -34
- data/docs/_sass/vendor/bourbon/addons/_triangle.scss +0 -63
- data/docs/_sass/vendor/bourbon/addons/_word-wrap.scss +0 -29
- data/docs/_sass/vendor/bourbon/css3/_animation.scss +0 -61
- data/docs/_sass/vendor/bourbon/css3/_appearance.scss +0 -5
- data/docs/_sass/vendor/bourbon/css3/_backface-visibility.scss +0 -5
- data/docs/_sass/vendor/bourbon/css3/_background-image.scss +0 -44
- data/docs/_sass/vendor/bourbon/css3/_background.scss +0 -57
- data/docs/_sass/vendor/bourbon/css3/_border-image.scss +0 -61
- data/docs/_sass/vendor/bourbon/css3/_calc.scss +0 -6
- data/docs/_sass/vendor/bourbon/css3/_columns.scss +0 -67
- data/docs/_sass/vendor/bourbon/css3/_filter.scss +0 -6
- data/docs/_sass/vendor/bourbon/css3/_flex-box.scss +0 -327
- data/docs/_sass/vendor/bourbon/css3/_font-face.scss +0 -29
- data/docs/_sass/vendor/bourbon/css3/_font-feature-settings.scss +0 -6
- data/docs/_sass/vendor/bourbon/css3/_hidpi-media-query.scss +0 -12
- data/docs/_sass/vendor/bourbon/css3/_hyphens.scss +0 -6
- data/docs/_sass/vendor/bourbon/css3/_image-rendering.scss +0 -15
- data/docs/_sass/vendor/bourbon/css3/_keyframes.scss +0 -38
- data/docs/_sass/vendor/bourbon/css3/_linear-gradient.scss +0 -40
- data/docs/_sass/vendor/bourbon/css3/_perspective.scss +0 -12
- data/docs/_sass/vendor/bourbon/css3/_placeholder.scss +0 -10
- data/docs/_sass/vendor/bourbon/css3/_radial-gradient.scss +0 -40
- data/docs/_sass/vendor/bourbon/css3/_selection.scss +0 -44
- data/docs/_sass/vendor/bourbon/css3/_text-decoration.scss +0 -27
- data/docs/_sass/vendor/bourbon/css3/_transform.scss +0 -21
- data/docs/_sass/vendor/bourbon/css3/_transition.scss +0 -81
- data/docs/_sass/vendor/bourbon/css3/_user-select.scss +0 -5
- data/docs/_sass/vendor/bourbon/functions/_assign-inputs.scss +0 -16
- data/docs/_sass/vendor/bourbon/functions/_contains-falsy.scss +0 -25
- data/docs/_sass/vendor/bourbon/functions/_contains.scss +0 -31
- data/docs/_sass/vendor/bourbon/functions/_is-length.scss +0 -16
- data/docs/_sass/vendor/bourbon/functions/_is-light.scss +0 -26
- data/docs/_sass/vendor/bourbon/functions/_is-number.scss +0 -16
- data/docs/_sass/vendor/bourbon/functions/_is-size.scss +0 -23
- data/docs/_sass/vendor/bourbon/functions/_modular-scale.scss +0 -74
- data/docs/_sass/vendor/bourbon/functions/_px-to-em.scss +0 -24
- data/docs/_sass/vendor/bourbon/functions/_px-to-rem.scss +0 -26
- data/docs/_sass/vendor/bourbon/functions/_shade.scss +0 -24
- data/docs/_sass/vendor/bourbon/functions/_strip-units.scss +0 -22
- data/docs/_sass/vendor/bourbon/functions/_tint.scss +0 -24
- data/docs/_sass/vendor/bourbon/functions/_transition-property-name.scss +0 -37
- data/docs/_sass/vendor/bourbon/functions/_unpack.scss +0 -32
- data/docs/_sass/vendor/bourbon/helpers/_convert-units.scss +0 -26
- data/docs/_sass/vendor/bourbon/helpers/_directional-values.scss +0 -108
- data/docs/_sass/vendor/bourbon/helpers/_font-source-declaration.scss +0 -53
- data/docs/_sass/vendor/bourbon/helpers/_gradient-positions-parser.scss +0 -24
- data/docs/_sass/vendor/bourbon/helpers/_linear-angle-parser.scss +0 -35
- data/docs/_sass/vendor/bourbon/helpers/_linear-gradient-parser.scss +0 -51
- data/docs/_sass/vendor/bourbon/helpers/_linear-positions-parser.scss +0 -77
- data/docs/_sass/vendor/bourbon/helpers/_linear-side-corner-parser.scss +0 -41
- data/docs/_sass/vendor/bourbon/helpers/_radial-arg-parser.scss +0 -74
- data/docs/_sass/vendor/bourbon/helpers/_radial-gradient-parser.scss +0 -55
- data/docs/_sass/vendor/bourbon/helpers/_radial-positions-parser.scss +0 -28
- data/docs/_sass/vendor/bourbon/helpers/_render-gradients.scss +0 -31
- data/docs/_sass/vendor/bourbon/helpers/_shape-size-stripper.scss +0 -15
- data/docs/_sass/vendor/bourbon/helpers/_str-to-num.scss +0 -55
- data/docs/_sass/vendor/bourbon/settings/_asset-pipeline.scss +0 -7
- data/docs/_sass/vendor/bourbon/settings/_deprecation-warnings.scss +0 -8
- data/docs/_sass/vendor/bourbon/settings/_prefixer.scss +0 -9
- data/docs/_sass/vendor/bourbon/settings/_px-to-em.scss +0 -1
- data/docs/_sass/vendor/neat/_neat-helpers.scss +0 -11
- data/docs/_sass/vendor/neat/_neat.scss +0 -23
- data/docs/_sass/vendor/neat/functions/_new-breakpoint.scss +0 -49
- data/docs/_sass/vendor/neat/functions/_private.scss +0 -114
- data/docs/_sass/vendor/neat/grid/_box-sizing.scss +0 -15
- data/docs/_sass/vendor/neat/grid/_direction-context.scss +0 -33
- data/docs/_sass/vendor/neat/grid/_display-context.scss +0 -28
- data/docs/_sass/vendor/neat/grid/_fill-parent.scss +0 -22
- data/docs/_sass/vendor/neat/grid/_media.scss +0 -92
- data/docs/_sass/vendor/neat/grid/_omega.scss +0 -87
- data/docs/_sass/vendor/neat/grid/_outer-container.scss +0 -34
- data/docs/_sass/vendor/neat/grid/_pad.scss +0 -25
- data/docs/_sass/vendor/neat/grid/_private.scss +0 -35
- data/docs/_sass/vendor/neat/grid/_row.scss +0 -52
- data/docs/_sass/vendor/neat/grid/_shift.scss +0 -50
- data/docs/_sass/vendor/neat/grid/_span-columns.scss +0 -94
- data/docs/_sass/vendor/neat/grid/_to-deprecate.scss +0 -97
- data/docs/_sass/vendor/neat/grid/_visual-grid.scss +0 -42
- data/docs/_sass/vendor/neat/mixins/_clearfix.scss +0 -25
- data/docs/_sass/vendor/neat/settings/_disable-warnings.scss +0 -13
- data/docs/_sass/vendor/neat/settings/_grid.scss +0 -51
- data/docs/_sass/vendor/neat/settings/_visual-grid.scss +0 -27
- data/docs/_sass/vendor/normalize-3.0.2.scss +0 -427
- data/docs/_sass/vendor/pygments.scss +0 -356
- data/docs/automating_browsers/capybara.md +0 -70
- data/docs/css/screen.scss +0 -7
- data/docs/guides/cli.md +0 -52
- data/docs/guides/frontiers.md +0 -93
- data/docs/guides/halting.md +0 -23
- data/docs/guides/job_queues.md +0 -26
- data/docs/guides/locals.md +0 -36
- data/docs/guides/logging.md +0 -22
- data/docs/guides/page_objects.md +0 -67
- data/docs/guides/peeking.md +0 -46
- data/docs/guides/selenium_capybara.md +0 -100
- data/docs/guides/tutorial.md +0 -452
- data/docs/js/navigation.js +0 -11
- data/docs/misc/contributing.md +0 -20
- data/docs/misc/testing.md +0 -11
- data/docs/recipes/authentication.md +0 -23
- data/docs/recipes/csv.md +0 -29
- data/docs/recipes/javascript.md +0 -20
- data/docs/recipes/multiple_uris.md +0 -18
- data/docs/recipes/screenshots.md +0 -20
- data/docs/routing/custom_rules.md +0 -16
- data/docs/routing/filetypes_rules.md +0 -21
- data/docs/routing/host_rules.md +0 -24
- data/docs/routing/path_rules.md +0 -33
- data/docs/routing/protocol_rules.md +0 -17
- data/docs/routing/query_rules.md +0 -69
- data/docs/routing/routes.md +0 -96
- data/docs/routing/uri_rules.md +0 -18
- data/examples/collect_github_issues.rb +0 -65
- data/examples/find_foobar_on_wikipedia.rb +0 -23
- data/lib/wayfarer/configuration.rb +0 -86
- data/lib/wayfarer/crawl.rb +0 -79
- data/lib/wayfarer/crawl_observer.rb +0 -103
- data/lib/wayfarer/dispatcher.rb +0 -104
- data/lib/wayfarer/finders.rb +0 -61
- data/lib/wayfarer/frontiers/frontier.rb +0 -79
- data/lib/wayfarer/frontiers/memory_bloomfilter.rb +0 -32
- data/lib/wayfarer/frontiers/memory_frontier.rb +0 -76
- data/lib/wayfarer/frontiers/memory_trie_frontier.rb +0 -39
- data/lib/wayfarer/frontiers/normalize_uris.rb +0 -48
- data/lib/wayfarer/frontiers/redis_bloomfilter.rb +0 -34
- data/lib/wayfarer/frontiers/redis_frontier.rb +0 -83
- data/lib/wayfarer/http_adapters/adapter_pool.rb +0 -62
- data/lib/wayfarer/http_adapters/net_http_adapter.rb +0 -77
- data/lib/wayfarer/http_adapters/selenium_adapter.rb +0 -80
- data/lib/wayfarer/job.rb +0 -211
- data/lib/wayfarer/locals.rb +0 -40
- data/lib/wayfarer/parsers/json_parser.rb +0 -20
- data/lib/wayfarer/parsers/xml_parser.rb +0 -27
- data/lib/wayfarer/processor.rb +0 -103
- data/lib/wayfarer/routing/custom_rule.rb +0 -21
- data/lib/wayfarer/routing/filetypes_rule.rb +0 -20
- data/lib/wayfarer/routing/host_rule.rb +0 -19
- data/lib/wayfarer/routing/path_rule.rb +0 -54
- data/lib/wayfarer/routing/protocol_rule.rb +0 -21
- data/lib/wayfarer/routing/router.rb +0 -71
- data/lib/wayfarer/routing/rule.rb +0 -114
- data/lib/wayfarer/routing/uri_rule.rb +0 -21
- data/spec/configuration_spec.rb +0 -26
- data/spec/crawl_spec.rb +0 -48
- data/spec/finders_spec.rb +0 -49
- data/spec/frontiers/memory_bloomfilter_spec.rb +0 -6
- data/spec/frontiers/memory_frontier_spec.rb +0 -6
- data/spec/frontiers/memory_trie_frontier_spec.rb +0 -6
- data/spec/frontiers/normalize_uris_spec.rb +0 -59
- data/spec/frontiers/redis_bloomfilter_spec.rb +0 -6
- data/spec/frontiers/redis_frontier_spec.rb +0 -6
- data/spec/http_adapters/adapter_pool_spec.rb +0 -33
- data/spec/http_adapters/net_http_adapter_spec.rb +0 -83
- data/spec/http_adapters/selenium_adapter_spec.rb +0 -53
- data/spec/integration/callbacks_spec.rb +0 -42
- data/spec/integration/locals_spec.rb +0 -106
- data/spec/integration/peeking_spec.rb +0 -61
- data/spec/job_spec.rb +0 -122
- data/spec/processor_spec.rb +0 -31
- data/spec/routing/custom_rule_spec.rb +0 -26
- data/spec/routing/host_rule_spec.rb +0 -48
- data/spec/routing/path_rule_spec.rb +0 -66
- data/spec/routing/protocol_rule_spec.rb +0 -26
- data/spec/routing/router_spec.rb +0 -67
- data/spec/routing/rule_spec.rb +0 -251
- data/spec/routing/uri_rule_spec.rb +0 -24
- data/spec/shared/frontier.rb +0 -96
- data/wayfarer-jruby.gemspec +0 -49
@@ -0,0 +1,47 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Middleware
|
5
|
+
module Worker
|
6
|
+
def self.included(base)
|
7
|
+
base.include(Wayfarer::Redis::Connection)
|
8
|
+
base.include(Wayfarer::Middleware::Stage::API)
|
9
|
+
base.include(InstanceMethods)
|
10
|
+
base.extend(ClassMethods)
|
11
|
+
end
|
12
|
+
|
13
|
+
module ClassMethods
|
14
|
+
def route
|
15
|
+
@route ||= Wayfarer::Routing::RootRoute.new.tap do |route|
|
16
|
+
Docile.dsl_eval(route) { yield if block_given? }
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
module InstanceMethods
|
22
|
+
extend Forwardable
|
23
|
+
|
24
|
+
attr_accessor :task
|
25
|
+
|
26
|
+
delegate %i[params adapter] => "task.metadata"
|
27
|
+
delegate %i[browser capybara] => :adapter
|
28
|
+
|
29
|
+
def call(task)
|
30
|
+
self.task = task
|
31
|
+
public_send(task.metadata.action)
|
32
|
+
yield if block_given?
|
33
|
+
end
|
34
|
+
|
35
|
+
def chain
|
36
|
+
Wayfarer::Middleware::Chain.new([*Wayfarer.core_middleware, self])
|
37
|
+
end
|
38
|
+
|
39
|
+
def page(live: false)
|
40
|
+
return task.metadata.page unless live
|
41
|
+
|
42
|
+
task.metadata.page = adapter.live(task.metadata.page)
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
@@ -0,0 +1,70 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Networking
|
5
|
+
class Ferrum
|
6
|
+
def self.renew_on
|
7
|
+
[::Ferrum::DeadBrowserError]
|
8
|
+
end
|
9
|
+
|
10
|
+
attr_reader :browser
|
11
|
+
|
12
|
+
def initialize
|
13
|
+
@browser = instantiate_browser
|
14
|
+
end
|
15
|
+
|
16
|
+
def fetch(url)
|
17
|
+
browser.goto(url)
|
18
|
+
Result::Success.new(live(nil))
|
19
|
+
end
|
20
|
+
|
21
|
+
def live(_)
|
22
|
+
Wayfarer::Page.new(url: browser.current_url,
|
23
|
+
body: body,
|
24
|
+
status_code: browser.network.response.status,
|
25
|
+
headers: browser.network.response.headers)
|
26
|
+
end
|
27
|
+
|
28
|
+
def body
|
29
|
+
browser.body
|
30
|
+
end
|
31
|
+
|
32
|
+
def renew
|
33
|
+
free
|
34
|
+
@browser = instantiate_browser
|
35
|
+
end
|
36
|
+
|
37
|
+
def free
|
38
|
+
browser&.reset
|
39
|
+
browser&.quit
|
40
|
+
@browser = nil
|
41
|
+
@capybara = nil
|
42
|
+
end
|
43
|
+
|
44
|
+
def capybara
|
45
|
+
@capybara ||= instantiate_capybara_driver
|
46
|
+
end
|
47
|
+
|
48
|
+
private
|
49
|
+
|
50
|
+
def instantiate_browser
|
51
|
+
::Ferrum::Browser.new(Wayfarer.config.ferrum_options).tap do |browser|
|
52
|
+
browser.headers.set(Wayfarer.config.http_headers)
|
53
|
+
end
|
54
|
+
end
|
55
|
+
|
56
|
+
def instantiate_capybara_driver
|
57
|
+
Capybara.run_server = false
|
58
|
+
Capybara.current_driver = :cuprite
|
59
|
+
|
60
|
+
capybara_driver = Capybara::Cuprite::Driver.new(nil)
|
61
|
+
capybara_driver.instance_variable_set(:@capybara, browser)
|
62
|
+
|
63
|
+
session = Capybara::Session.new(:cuprite, nil)
|
64
|
+
session.instance_variable_set(:@driver, capybara_driver)
|
65
|
+
|
66
|
+
session
|
67
|
+
end
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
# An adapter that renews another adapter on certain errors.
|
4
|
+
# This wrapper is required because connection_pool assumes
|
5
|
+
# all connections are self-healing.
|
6
|
+
module Wayfarer
|
7
|
+
module Networking
|
8
|
+
Healer = Struct.new(:adapter) do
|
9
|
+
extend Forwardable
|
10
|
+
|
11
|
+
delegate %i[body browser capybara free] => :adapter
|
12
|
+
|
13
|
+
def fetch(url)
|
14
|
+
adapter.fetch(url)
|
15
|
+
rescue *adapter.class.renew_on => e
|
16
|
+
adapter.renew
|
17
|
+
raise e
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
@@ -0,0 +1,52 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Networking
|
5
|
+
class NetHTTP
|
6
|
+
include Singleton
|
7
|
+
|
8
|
+
def self.renew_on
|
9
|
+
[]
|
10
|
+
end
|
11
|
+
|
12
|
+
attr_reader :conn,
|
13
|
+
:body
|
14
|
+
|
15
|
+
def initialize
|
16
|
+
@conn = Net::HTTP::Persistent.new("wayfarer-#{SecureRandom.uuid}")
|
17
|
+
|
18
|
+
Wayfarer.config.http_headers.each do |key, val|
|
19
|
+
conn.override_headers[key] = val
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
def renew; end
|
24
|
+
|
25
|
+
def browser; end
|
26
|
+
|
27
|
+
def capybara; end
|
28
|
+
|
29
|
+
def fetch(url)
|
30
|
+
res = conn.request(URI(url))
|
31
|
+
|
32
|
+
return Result::Redirect.new(url, res["location"]) if res.is_a?(Net::HTTPRedirection)
|
33
|
+
|
34
|
+
@body = res.body
|
35
|
+
page = Wayfarer::Page.new(url: url,
|
36
|
+
status_code: res.code.to_i,
|
37
|
+
body: body,
|
38
|
+
headers: res.to_hash)
|
39
|
+
|
40
|
+
Result::Success.new(page)
|
41
|
+
end
|
42
|
+
|
43
|
+
def live(current_page)
|
44
|
+
current_page
|
45
|
+
end
|
46
|
+
|
47
|
+
def free
|
48
|
+
conn.shutdown
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
@@ -0,0 +1,34 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Networking
|
5
|
+
class Pool
|
6
|
+
include Singleton
|
7
|
+
extend Forwardable
|
8
|
+
|
9
|
+
attr_reader :pool
|
10
|
+
|
11
|
+
def initialize
|
12
|
+
@pool = ConnectionPool.new(size: Wayfarer.config.adapter_pool_size,
|
13
|
+
timeout: Wayfarer.config.adapter_pool_timeout,
|
14
|
+
&method(:instantiate_adapter))
|
15
|
+
end
|
16
|
+
|
17
|
+
delegate with: :pool
|
18
|
+
|
19
|
+
def free
|
20
|
+
pool.shutdown(&:free)
|
21
|
+
end
|
22
|
+
|
23
|
+
private
|
24
|
+
|
25
|
+
def instantiate_adapter
|
26
|
+
Healer.new(case Wayfarer.config.adapter
|
27
|
+
when :net_http then Wayfarer::Networking::NetHTTP.instance
|
28
|
+
when :selenium then Wayfarer::Networking::Selenium.new
|
29
|
+
when :ferrum then Wayfarer::Networking::Ferrum.new
|
30
|
+
end)
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
34
|
+
end
|
@@ -0,0 +1,18 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Networking
|
5
|
+
# Wrapper structs for page retrieval results.
|
6
|
+
module Result
|
7
|
+
# Signals that a page has been retrieved (2xx or no browser error).
|
8
|
+
# @!attribute [rw] page
|
9
|
+
# @return [Page] the retrieved page.
|
10
|
+
Success = Struct.new(:page)
|
11
|
+
|
12
|
+
# Signals that a URL resulted in response with 3xx.
|
13
|
+
# @!attribute [rw] redirect_url
|
14
|
+
# @return [URI] Where to go next.
|
15
|
+
Redirect = Struct.new(:request_url, :redirect_url)
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
@@ -0,0 +1,70 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Networking
|
5
|
+
class Selenium
|
6
|
+
def self.renew_on
|
7
|
+
[] # TODO: Figure out when to renew
|
8
|
+
end
|
9
|
+
|
10
|
+
FAKE_STATUS_CODE = 200
|
11
|
+
FAKE_RESPONSE_HEADERS = {}.freeze
|
12
|
+
|
13
|
+
attr_reader :browser
|
14
|
+
|
15
|
+
def initialize
|
16
|
+
@browser = instantiate_browser
|
17
|
+
end
|
18
|
+
|
19
|
+
def fetch(url)
|
20
|
+
browser.navigate.to(url)
|
21
|
+
Result::Success.new(live(nil))
|
22
|
+
end
|
23
|
+
|
24
|
+
def live(_)
|
25
|
+
Wayfarer::Page.new(url: browser.current_url,
|
26
|
+
body: browser.page_source,
|
27
|
+
status_code: FAKE_STATUS_CODE,
|
28
|
+
headers: FAKE_RESPONSE_HEADERS)
|
29
|
+
end
|
30
|
+
|
31
|
+
def body
|
32
|
+
browser.page_source
|
33
|
+
end
|
34
|
+
|
35
|
+
def renew
|
36
|
+
free
|
37
|
+
@browser = instantiate_browser
|
38
|
+
end
|
39
|
+
|
40
|
+
def free
|
41
|
+
browser&.quit
|
42
|
+
@browser = nil
|
43
|
+
@capybara = nil
|
44
|
+
end
|
45
|
+
|
46
|
+
def capybara
|
47
|
+
@capybara ||= instantiate_capybara_driver
|
48
|
+
end
|
49
|
+
|
50
|
+
private
|
51
|
+
|
52
|
+
def instantiate_browser
|
53
|
+
::Selenium::WebDriver.for(*Wayfarer.config.selenium_argv)
|
54
|
+
end
|
55
|
+
|
56
|
+
def instantiate_capybara_driver
|
57
|
+
Capybara.run_server = false
|
58
|
+
Capybara.current_driver = :selenium
|
59
|
+
|
60
|
+
capybara_driver = Capybara::Selenium::Driver.new(nil)
|
61
|
+
capybara_driver.instance_variable_set(:@capybara, browser)
|
62
|
+
|
63
|
+
session = Capybara::Session.new(:selenium, nil)
|
64
|
+
session.instance_variable_set(:@driver, capybara_driver)
|
65
|
+
|
66
|
+
session
|
67
|
+
end
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
data/lib/wayfarer/page.rb
CHANGED
@@ -1,94 +1,38 @@
|
|
1
1
|
# frozen_string_literal: true
|
2
2
|
|
3
|
-
require "ostruct"
|
4
|
-
require "forwardable"
|
5
|
-
require "mime/types"
|
6
|
-
require "mime-types"
|
7
|
-
|
8
|
-
require "pismo" unless RUBY_PLATFORM == "java"
|
9
|
-
|
10
3
|
module Wayfarer
|
11
|
-
# The representation of fetched pages
|
12
4
|
class Page
|
13
|
-
|
14
|
-
|
15
|
-
|
5
|
+
attr_reader :url,
|
6
|
+
:status_code,
|
7
|
+
:headers
|
16
8
|
|
17
|
-
# @!attribute [r] uri
|
18
|
-
# @return [URI] the URI of the page.
|
19
|
-
attr_reader :uri
|
20
|
-
|
21
|
-
# @!attribute [r] status_code
|
22
|
-
# @return [Fixnum] the response status code.
|
23
|
-
attr_reader :status_code
|
24
|
-
|
25
|
-
# @!attribute [r] body
|
26
|
-
# @return [String] the response body.
|
27
9
|
attr_accessor :body
|
28
10
|
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
@uri = attrs[:uri]
|
35
|
-
@status_code = attrs[:status_code]
|
36
|
-
@body = attrs[:body]
|
37
|
-
@headers = attrs[:headers]
|
11
|
+
def initialize(url:, status_code:, headers:, body:)
|
12
|
+
@url = url
|
13
|
+
@status_code = status_code
|
14
|
+
@body = body
|
15
|
+
@headers = headers.transform_keys(&:downcase)
|
38
16
|
end
|
39
17
|
|
40
|
-
# Returns a parsed representation of the fetched document depending on the
|
41
|
-
# Content-Type field.
|
42
|
-
# @return [OpenStruct] if the Content-Type field's sub-type is "json".
|
43
|
-
# @return [Nokogiri::XML::Document] if the Content-Type field's sub-type is "xml".
|
44
|
-
# @return [Nokogiri::HTML::Document] otherwise.
|
45
18
|
def doc
|
46
19
|
return @doc if @doc
|
47
20
|
|
48
21
|
# If no Content-Type field is present, assume HTML/XML
|
49
|
-
|
50
|
-
unless @headers["content-type"]
|
51
|
-
return @doc = Parsers::XMLParser.parse_html(@body)
|
52
|
-
end
|
22
|
+
return @doc = Wayfarer::Parsing::XML.parse_html(body) unless headers["content-type"]
|
53
23
|
|
54
|
-
content_type =
|
24
|
+
content_type = headers["content-type"].first
|
55
25
|
sub_type = MIME::Types[content_type].first.sub_type
|
56
26
|
|
57
|
-
# TODO: Tests
|
58
27
|
@doc = case sub_type
|
59
|
-
when "json"
|
60
|
-
|
61
|
-
|
62
|
-
Parsers::XMLParser.parse_xml(@body)
|
63
|
-
else
|
64
|
-
Parsers::XMLParser.parse_html(@body)
|
28
|
+
when "json" then Wayfarer::Parsing::JSON.parse(body)
|
29
|
+
when "xml" then Wayfarer::Parsing::XML.parse_xml(body)
|
30
|
+
else Wayfarer::Parsing::XML.parse_html(body)
|
65
31
|
end
|
66
32
|
end
|
67
33
|
|
68
|
-
|
69
|
-
|
70
|
-
# `#images` is included from the Helpers module
|
71
|
-
# `#body` is an attribute reader defined above
|
72
|
-
delegate (Pismo::Document::ATTRIBUTE_METHODS - %i[images body]) => :pismo
|
73
|
-
end
|
74
|
-
|
75
|
-
private
|
76
|
-
|
77
|
-
# Returns a Pismo document.
|
78
|
-
# @note Not available on JRuby.
|
79
|
-
# @note Only succeeds when {#doc} returns a `Nokogiri::HTML::Document`.
|
80
|
-
# @return [Pismo::Document]
|
81
|
-
def pismo
|
82
|
-
@pismo_doc ||= instantiate_pismo_document
|
83
|
-
end
|
84
|
-
|
85
|
-
def instantiate_pismo_document
|
86
|
-
doc = Pismo::Document.allocate
|
87
|
-
doc.instance_variable_set(:@options, {})
|
88
|
-
doc.instance_variable_set(:@url, uri)
|
89
|
-
doc.instance_variable_set(:@html, body)
|
90
|
-
doc.instance_variable_set(:@doc, self.doc)
|
91
|
-
doc
|
34
|
+
def meta
|
35
|
+
@meta ||= MetaInspector.new(url, document: body)
|
92
36
|
end
|
93
37
|
end
|
94
38
|
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Redis
|
5
|
+
Barrier = Struct.new(:batch) do
|
6
|
+
include Connection
|
7
|
+
|
8
|
+
def redis_key
|
9
|
+
"wayfarer-barrier-#{batch}"
|
10
|
+
end
|
11
|
+
|
12
|
+
def reset!
|
13
|
+
redis { |conn| conn.del(redis_key) }
|
14
|
+
end
|
15
|
+
|
16
|
+
def seen?(url)
|
17
|
+
!redis { |conn| conn.sadd(redis_key, url) }
|
18
|
+
end
|
19
|
+
|
20
|
+
def peek(urls)
|
21
|
+
major, minor, = Version.determine
|
22
|
+
|
23
|
+
# SMISMEMBER is only supported on Redis >= 6.2.0
|
24
|
+
if major > 6 || (major == 6 && minor >= 2)
|
25
|
+
redis { |conn| conn.smismember(redis_key, urls) }.map { |val| val == 1 }
|
26
|
+
else
|
27
|
+
urls.map { |url| redis { |conn| conn.sismember(redis_key, url) } }
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
def unsee(url)
|
32
|
+
redis { |conn| conn.srem(redis_key, url) }
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Redis
|
5
|
+
Counter = Struct.new(:batch) do
|
6
|
+
include Connection
|
7
|
+
|
8
|
+
def redis_key
|
9
|
+
"wayfarer-counter-#{batch}"
|
10
|
+
end
|
11
|
+
|
12
|
+
def reset!
|
13
|
+
redis { |conn| conn.del(redis_key) }
|
14
|
+
end
|
15
|
+
|
16
|
+
def value
|
17
|
+
redis { |conn| conn.get(redis_key) }.to_i
|
18
|
+
end
|
19
|
+
|
20
|
+
def increment
|
21
|
+
redis { |conn| conn.incr(redis_key) }
|
22
|
+
end
|
23
|
+
|
24
|
+
def decrement
|
25
|
+
redis { |conn| conn.decr(redis_key) }
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,18 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Redis
|
5
|
+
class Pool
|
6
|
+
include Singleton
|
7
|
+
extend Forwardable
|
8
|
+
|
9
|
+
attr_reader :pool
|
10
|
+
|
11
|
+
def initialize
|
12
|
+
@pool = ConnectionPool.new(&Wayfarer.config.redis_factory)
|
13
|
+
end
|
14
|
+
|
15
|
+
delegate with: :pool
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
@@ -0,0 +1,19 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Redis
|
5
|
+
module Version
|
6
|
+
extend Connection
|
7
|
+
|
8
|
+
module_function
|
9
|
+
|
10
|
+
def determine
|
11
|
+
@determine ||= server_version.split(".").first(3).map(&:to_i)
|
12
|
+
end
|
13
|
+
|
14
|
+
def server_version
|
15
|
+
redis { |conn| conn.info["redis_version"] }
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,21 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Routing
|
5
|
+
class CustomMatcher
|
6
|
+
attr_reader :delegate
|
7
|
+
|
8
|
+
def initialize(delegate = proc)
|
9
|
+
@delegate = delegate
|
10
|
+
end
|
11
|
+
|
12
|
+
def match(url)
|
13
|
+
!!delegate.call(url)
|
14
|
+
end
|
15
|
+
|
16
|
+
def params(_)
|
17
|
+
{}
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
@@ -0,0 +1,57 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Routing
|
5
|
+
module DSL
|
6
|
+
def url(url, options = {}, &block)
|
7
|
+
add_child_route(URLMatcher.new(url), path_offset, options, &block)
|
8
|
+
end
|
9
|
+
|
10
|
+
def host(host, options = {}, &block)
|
11
|
+
add_child_route(HostMatcher.new(host), path_offset, options, &block)
|
12
|
+
end
|
13
|
+
|
14
|
+
def path(path, options = {}, &block)
|
15
|
+
offset = File.join(path_offset, path)
|
16
|
+
add_child_route(nil, offset, options, &block).tap do |route|
|
17
|
+
route.matcher = PathMatcher.new(offset, route)
|
18
|
+
end
|
19
|
+
end
|
20
|
+
|
21
|
+
def query(fields, options = {}, &block)
|
22
|
+
add_child_route(QueryMatcher.new(fields), path_offset, options, &block)
|
23
|
+
end
|
24
|
+
|
25
|
+
def scheme(scheme, options = {}, &block)
|
26
|
+
add_child_route(SchemeMatcher.new(scheme), path_offset, options, &block)
|
27
|
+
end
|
28
|
+
|
29
|
+
def suffix(suffix, options = {}, &block)
|
30
|
+
add_child_route(SuffixMatcher.new(suffix), path_offset, options, &block)
|
31
|
+
end
|
32
|
+
|
33
|
+
def to(action, options = {}, &block)
|
34
|
+
add_child_route(CustomMatcher.new { true }, path_offset, TargetRoute, options, &block).tap do |route|
|
35
|
+
route.action = action
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
def custom(delegate, options = {}, &block)
|
40
|
+
add_child_route(CustomMatcher.new(delegate), path_offset, options, &block)
|
41
|
+
end
|
42
|
+
|
43
|
+
private
|
44
|
+
|
45
|
+
# rubocop:disable Style/OptionalArguments
|
46
|
+
def add_child_route(matcher, path_offset, klass = Route, options, &block)
|
47
|
+
klass.new(matcher, path_offset, &block).tap do |route|
|
48
|
+
route.parent = self
|
49
|
+
leaf = options.reduce(route) { |acc, (key, val)| acc.public_send(key, val) }
|
50
|
+
children.push(route)
|
51
|
+
Docile.dsl_eval(leaf, &block) if block_given?
|
52
|
+
end
|
53
|
+
end
|
54
|
+
# rubocop:enable Style/OptionalArguments
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
@@ -0,0 +1,23 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module Wayfarer
|
4
|
+
module Routing
|
5
|
+
class HostMatcher
|
6
|
+
attr_reader :host
|
7
|
+
|
8
|
+
def initialize(host)
|
9
|
+
@host = host
|
10
|
+
end
|
11
|
+
|
12
|
+
# rubocop:disable Style/CaseEquality
|
13
|
+
def match(url)
|
14
|
+
@host === url.host
|
15
|
+
end
|
16
|
+
# rubocop:enable Style/CaseEquality
|
17
|
+
|
18
|
+
def params(_)
|
19
|
+
{}
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|